AIShield - Tabular classification AI Model extraction high suspicious vulnerability detection

Back


Id	8d03e3ff-18eb-497c-a6cb-1c35ccdb0ed3
Rulename	AIShield - Tabular classification AI Model extraction high suspicious vulnerability detection
Description	This alert creates an incident when Tabular classification AI Model extraction high suspicious, high severity vulnerability detected from the AIShield.
Severity	High
Required data connectors	BoschAIShield
Kind	Scheduled
Query frequency	1h
Query period	1h
Trigger threshold	0
Trigger operator	gt
Source Uri	https://github.com/Azure/Azure-Sentinel/blob/master/Solutions/AIShield AI Security Monitoring/Analytic Rules/TabularClassificationModelExtractionHighSuspiciousVulnDetection.yaml
Version	1.0.4
Arm template	8d03e3ff-18eb-497c-a6cb-1c35ccdb0ed3.json

KQL

AIShield
| where Message has 'Tabular Classification AI Model Extraction Attack Identified'
| where Severity =~ 'High'
| where SuspiciousLevel =~ 'high suspicious attack'
| extend NTDomain = tostring(split(Computer, '\\')[0]), HostName = tostring(split(Computer, '.')[0])

YAML

queryFrequency: 1h
kind: Scheduled
version: 1.0.4
relevantTechniques: []
alertDetailsOverride:
  alertDisplayNameFormat: AIShield - Tabular Classification AI Model extraction high suspicious vulnerability detected.
  alertDescriptionFormat: |
        This query detects Tabular Classification AI Model extraction high suspicious, high severity alert from AIShield generated at {{TimeGenerated}}.\n\nPlease check the source for more information and investigate further.
  alertSeverityColumnName: Severity
  alertTacticsColumnName: 
triggerOperator: gt
status: Available
requiredDataConnectors:
- connectorId: BoschAIShield
  dataTypes:
  - AIShield
id: 8d03e3ff-18eb-497c-a6cb-1c35ccdb0ed3
name: AIShield - Tabular classification AI Model extraction high suspicious vulnerability detection
query: |
  AIShield
  | where Message has 'Tabular Classification AI Model Extraction Attack Identified'
  | where Severity =~ 'High'
  | where SuspiciousLevel =~ 'high suspicious attack'
  | extend NTDomain = tostring(split(Computer, '\\')[0]), HostName = tostring(split(Computer, '.')[0])  
queryPeriod: 1h
OriginalUri: https://github.com/Azure/Azure-Sentinel/blob/master/Solutions/AIShield AI Security Monitoring/Analytic Rules/TabularClassificationModelExtractionHighSuspiciousVulnDetection.yaml
triggerThreshold: 0
description: |
    'This alert creates an incident when Tabular classification AI Model extraction high suspicious, high severity vulnerability detected from the AIShield.'
entityMappings:
- entityType: Host
  fieldMappings:
  - identifier: HostName
    columnName: HostName
  - identifier: NTDomain
    columnName: NTDomain
- entityType: IP
  fieldMappings:
  - identifier: Address
    columnName: SourceName
severity: High
tactics: []
eventGroupingSettings:
  aggregationKind: SingleAlert

ARM